Forgot your password?
typodupeerror
Programming

An Open Source Compiler From CUDA To X86-Multicore 71

Gregory Diamos writes "An open source project, Ocelot, has recently released a just-in-time compiler for CUDA, allowing the same programs to be run on NVIDIA GPUs or x86 CPUs and providing an alternative to OpenCL. A description of the compiler was recently posted on the NVIDIA forums. The compiler works by translating GPU instructions to LLVM and then generating native code for any LLVM target. It has been validated against over 100 CUDA applications. All of the code is available under the New BSD license."

Comment Re:c ? really? (Score 1) 766

Multicore CPUs are likely to kill C.

IMHO, as long as one can spin any thread in C, having multicore CPUs should be transparent. It is duty of the underlaying multi-core-aware OS to manage your C threads onto multi-core/multi-processor platform.

... These aren't so important in a single thread, but they are when you introduce parallelism.

These concepts have been in play ever since. Using synchronization object and taking multi-threading precautions will perfectly do it for C as well. Posix anyone? PThread libs? OpenMPI?

Slashdot Top Deals

Support bacteria -- it's the only culture some people have!

Working...